A Novel Risk Indicator for Cut-In Situations

This paper presents a probabilistic decision-making framework for rear-end collision avoidance systems, focusing on modeling the impact of major collision-causing factors on the occurrence of accidents. Decisions on when and how to assist drivers are made using a Bayesian network approach according to collision risk evaluation results, given a prior probabilistic knowledge. The structure of the Bayesian network model is learnt using a K2 algorithm with a practical dataset. To provide adequate response time for drivers, we also predict collision probability in the next monitoring interval using a Kalman filter model. The prediction accuracy is evaluated with different use cases and compared to real scenarios with the obtained dataset. To make our framework more relevant to practical applications, we also discuss the corresponding safety control strategies by classifying collision risk into high and low levels. In addition, the proposed model is evaluated through experiments including simulations and road tests. In the simulations, the algorithms are tested in different scenarios with various configurations of weather conditions, driver response capability, and vehicular dynamics. In order to demonstrate collision avoidance performance, the proposed model is also compared to existing schemes. In the road tests, the algorithm is embedded into an unmanned vehicle with predefined parameters to evaluate the impact of computational complexity on rear-end collision avoidance. Numerical results show that the proposed model provides an accurate estimation for car-following collision risk with a relatively low complexity, taking into account the impacts of vehicle dynamics, driver reaction capacity, and external environment on rear-end collisions.

There are various kinds of indices to evaluate collision risk against forward obstacles, which are used to determine the timing of collision warning provision in forward obstacle collision warning systems (FCWSs) and advanced emergency braking systems. A previous study proposed a deceleration for collision avoidance (DCA) method, which can evaluate a collision risk more precisely than other conventional indices. However, the calculation process of DCA assumed that a following vehicle (FV) performs a uniform motion within a driver's constant reaction time. The assumption causes underestimation of collision risk when the FV accelerates and overestimation when it decelerates. Consequently, this paper shows a detailed calculation process of an improved DCA based on an expanded assumption that the FV maintains a uniformly accelerated motion within the reaction time. Moreover, stimulus-response experiments were conducted to measure the driver's reaction time when he/she adjusts the brake pedal depression. Numerical simulations, where DCA is used for the FCWS, were performed to show that the improved DCA (with a new setting for the driver reaction time) describes the collision risk more properly compared to the conventional DCA.

Rear-end collision is a main type of traffic accidents. In this study, we divided collision risks of car-following cases into three types, potential risk, obvious risk, and driver’s subjective risk perception. We designed different experiments to examine performance and parameters of six collision risk judgment indices which have been proposed (e.g. TTC, THW) in the paper under these three types of collision risks. On that basis, we developed a new risk index and called it as “Driver Risk Perception”.KeywordsRear-end collisionsRisk judgment indicesRisk perceptionDriverSafety

Various collision avoidance systems (CASs) have been developed and employed in human-operated vehicles as well as more recently in autonomous vehicles. Most of the existing CASs perform an override function to actuate automatic emergency braking in a critical situation based on the current traffic information obtained from in-vehicle sensors or short-range vehicular communications. These CASs focus on the critical situation in the vicinity of the subject vehicle, which means they may have negative influences on the subject vehicle and its following vehicles, particularly when the leader vehicle of a platoon with short headway applies harsh braking to mitigate an impending collision risk. This study proposes a risk predictive CAS (RPCAS) which executes predictive deceleration with mild braking in advance to prevent a potential rear-end collision by predicting the collision risk arising from a downstream site. To evaluate the performance of the RPCAS, the proposed system is compared with several existing CASs in various car-following cases based on a microscopic traffic simulation. The simulation results show that the RPCAS can effectively reduce the rear-end collision risk with less harsh braking compared with the existing CASs. Furthermore, the RPCAS enables vehicles arriving from upstream to anticipate a potential crash, which provides them with sufficient time to reduce their current speeds proactively. The research findings suggest that the proposed system can attenuate the negative impacts of the previous CASs in relation to traffic and vehicular safety.

Objective Two-vehicle collision crashes are always tough challenges for traffic management departments due to its severe consequences. This study aims to investigate risk mechanism of three types of two-vehicle collisions (i.e., head on, sideswipe, and rear end) in the same city from a comprehensive perspective. Methods A random parameters binary logit framework was employed to capture the unobserved heterogeneity across individual observations and reveal potential correlations between risk indicators of injury severity. Results The results indicate that the correlated random parameters model performs best, and the impacts of risk indicators involving unsafe driving behavior and driver, vehicle, roadway, environment, and temporal characteristics on two-vehicle collisions are quite different. Based on the determinants of each two-vehicle collision, some recommendations have been proposed to improve the level of road traffic safety. Conclusions Fatal collisions are more likely to happen when driving on the roads with higher road function classification and involving the presence of heavy trucks. Road type, weather condition, and unsafe driving behavior are primary contributors to two-vehicle collisions. Besides, fatal head-on collisions are prone to occurring when exceeding speed limits and driving on rainy days. Illegal overtaking or lane changing significantly increases the risk of fatal injuries in both sideswipe and rear-end collisions. Moreover, significant correlations between the on-ramp of highways and violating traffic lights or signs, and between cloudy days and visibility range within 50–100 m, are identified in the injury severity models of sideswipe and rear-end collisions, respectively. Current findings suggest that more attention should be devoted to intervening unsafe driving behaviors for sideswipe collisions, as well as enhancing the provision of visibility range information to mitigate rear-end collisions in adverse weather conditions.

The primary function of a collision risk index is to determine the time when ships take action to avoid a collision. In this study, based on the complex non‐linear relationship between the collision risk degree and its influencing factors, classification and regression trees (CARTs) are applied to construct a prediction model for ship collision risk. The fuzzy comprehensive evaluation method is used to evaluate the risk of ship encounter samples to build a collision risk identification library containing expert collision avoidance experience information. The authors’ proposed CART regression model is trained using the samples in this identification library to develop a collision risk prediction model based on the CART. Their experimental results show that their proposed CART prediction model is better that the existing ship collision risk prediction model in terms of prediction accuracy and prediction speed when the feature dimension is low and the sample size is small.

CAV-enabled data analytics for enhancing adaptive signal control safety environment

To improve collision risk prediction in high-traffic coastal waters and support real-time decision-making in maritime navigation, this study proposes a regional collision risk prediction system integrating the Computed Distance at Collision (CDC) method with an Adaptive Neuro-Fuzzy Inference System (ANFIS). Unlike Distance at Closest Point of Approach (DCPA), which depends on the position of Global Positioning System (GPS) antennas, Computed Distance at Collision (CDC) directly reflects the actual hull shape and potential collision point. This enables a more realistic assessment of collision risk by accounting for the hull geometry and boundary conditions specific to different ship types. The system was designed and validated using ship motion simulations involving bulk and container ships across varying speeds and crossing angles. The CDC method was used to define collision, almost-collision, and near-collision situations based on geometric and hydrodynamic criteria. Subsequently, the FIS–CDC model was constructed using the ANFIS by learning patterns in collision time and distance under each condition. A total of four input variables—ship speed, crossing angle, remaining time, and remaining distance—were used to infer the collision risk index (CRI), allowing for a more nuanced and vessel-specific assessment than traditional CPA-based indicators. Simulation results show that the time to collision decreases with higher speeds and increases with wider crossing angles. The bulk carrier exhibited a wider collision-prone angle range and a greater sensitivity to speed changes than the container ship, highlighting differences in maneuverability and risk response. The proposed system demonstrated real-time applicability and accurate risk differentiation across scenarios. This research contributes to enhancing situational awareness and proactive risk mitigation in Maritime Autonomous Surface Ship (MASS) and Vessel Traffic System (VTS) environments. Future work will focus on real-time CDC optimization and extending the model to accommodate diverse ship types and encounter geometries.

Considering that collision accidents happen sometimes, it is necessary to predict the collision risk to ensure navigation safety. With the information construction in maritime and the popularity of automatic identification system application, it is more convenient to obtain ship navigation dynamics. How to obtain ship encounter dynamic parameters through automatic identification system information, assess ship collision risk, find out dangerous target ships, and give early warning and guarantee for ship navigation safety, is a problem that scholars have been studying. As an index to measure the degree of ship collision risk, CRI, namely, collision risk index, is usually obtained by calculating ship encounter parameters and comprehensive analysis. There are many factors that affect CRI, and the values of many parameters depend on expert judgment. The corresponding CRI has nonlinear and complex characteristics, which is highly correlated with the time sequence. In order to enhance the prediction accuracy and efficiency, PSO-LSTM neural network is applied in the paper to predict CRI. Experiments show that PSO-LSTM neural network can effectively predict collision risk and provide a reference for navigation safety.

Modeling collision risk for unsafe lane-changing behavior: A lane-changing risk index approach

An airport pick-up area is one of the most congested transportation facilities. When vehicles go to pick up passengers, they need to frequently change lanes to stop to pick up and leave, resulting in a high collision risk and congestion at pick-up areas. This study aims to investigate safety and efficiency of airport pick-up areas and extract traffic conflicts based on video data. The video data are collected from Changsha Airport in China, and vehicle trajectory data are extracted using Baidu API. The transformation between pixel coordinates and real coordinates is realized through homography transformation, and a GIS tool is used to match the lane data. At the same time, the trajectory is smoothed using Savitzky-Golay filtering. Safety risk indicators: time-to-collision (TTC), modified time-to-collision (MTTC), post-encroachment time (PET), and deceleration rate to avoid collision (DRAC) are utilized to evaluate vehicle collision risks. Modified CUSBoost algorithm is applied for imbalanced trajectory data classification based on four risk indicators and spatial distribution and features of different classes are detected. The results demonstrate that traffic conflicts at pick-up areas are caused by frequent lane changes that lead to overlapping vehicle trajectories and short following distances. It is expected that the findings from this study could help engineers and airport ground transportation managers design and implement effective solutions to enhance safety and efficiency at airport pick-up areas.

In the conditions of bad weather, the small vessels maneuvering ability of collision avoidance is seriously reduced and the vulnerability to maritime accidents increases due to the influence of strong wind and wave. This paper proposes a collision avoidance decision-making and control method for small vessels using the integrated collision risk assessment based on fuzzy logic. First, the speed of wind and height of wave in the bad weather conditions are fuzzified. Then, the collision risk indices are selected for fuzzy inference to get the basic collision risk which will be integrated with the vulnerability to collision accidents and it helps to improve the accuracy of collision risk assessment. According to the current multi-ships encounter situations, the similar cases are retrieved from the case database, and the collision avoidance decision is given after fuzzy adjustments. To implement collision avoidance actions, a fuzzy algorithm for nonlinear ship heading dynamic surface control (DSC) control considering input saturation and uncertainties is designed. The problem of "computational expansion" that may occur in high-order systems is avoided by using DSC technology. Finally, simulation experiments are implemented to verify the effectiveness of the collision avoidance method.

Why anticipatory sensing matters in commercial ACC systems under cut-in scenarios: A perspective from stochastic safety analysis.

Utilization of renewable energy is essential for climate change mitigation measures. Wind power generation, solar power generation, geothermal power generation, and biomass power generation have already been put into practical use, and numerical targets of establishment of these stations have been set for reducing carbon dioxide emissions in many countries. However, birds and bats collide with wind turbines. Opposition movements are taking place in various parts of Japan, including wild bird conservation groups. The raptor white-tailed eagle (Haliaeetus albicilla) actually has many collisions in Japan. This species has a resident population and a wintering population in Japan and is listed as an endangered species in Japan. Endangered white-fronted geese (Anser albifrons) and swans, whose populations were once reduced due to endocrine disrupters including DDTs, are also strictly protected, which are used to be a reason for reductions in the number of installations and operational restrictions of wind turbines, in the environmental impact assessment. However, there are no or very few cases of migratory birds colliding. Introducing the concept of risk into environmental impact assessments cannot reduce conflicts to zero, but it could reduce the number of conflicts so that they do not affect population persistence. For that purpose, adaptive risk management that monitors the number of individuals and the number of collisions and limits the operation of the facility when the number of collisions becomes excessive is effective. In addition, we will explain what kind of consensus was reached on the flight route of white-fronted geese.

Summary1. The global growth of wind energy has outpaced our assessment of possible impacts on wildlife. There is a pressing need for studies with pre‐ and post‐construction data to determine whether wind facilities will have detrimental effects on susceptible avian groups such as raptors.2. A pre‐ and post‐construction study was conducted to determine the impact of a windfarm on the abundance and behaviour of raptors in Wisconsin, USA. Variation in abundance and behaviour was examined both within and among years and relative to selected spatial, temporal and weather covariates. Raptor avoidance rates and indices of collision risk were calculated.3. Raptor abundance post‐construction was reduced by 47% compared to pre‐construction levels. Flight behaviour varied by species, but most individuals remained at a distance of at least 100 m from turbines and above the height of the rotor zone.4. Turkey vultures Cathartes aura and red‐tailed hawks Buteo jamaicensis displayed high‐risk flight behaviours more often than all other raptor species, but also showed signs of avoidance. Red‐tailed hawks were the only raptor species found dead beneath turbines during mortality searches. There were few observed mortalities and corrected mortality estimates were comparable to those from other windfarm studies.5. Synthesis and applications. The decline in raptor abundance post‐construction together with other lines of evidence suggests some displacement from the windfarm project area. While certain species may be at risk, flight behaviour data and mortality estimates indicate that the majority of raptors may not be directly affected by the presence of turbines. The avoidance rates recorded in this study should be used to improve collision risk models, and both current and future windfarms should investigate avoidance behaviour post‐construction.